11 May, 2020

h2.title { font-size: 8px; #color: #a9a9a9; text-align: center; }

Introduction

Dataset:

  • breast cancer

  • proteomics by mass spectrometry

Goal:

  • Explore the dataset for patterns

  • Create models to identify the breast cancer subclasses

Material and Methods

The data set

Material and Methods

Material and Methods

  • Exploratory analysis

  • PCA

  • K-means

  • ANN

Material and Methods

Results — no definitive effects between expression landscapes and specific tumor subclasses

Results — breast cancer subtypes in the dataset are well represented

Results — breast cancer subtypes do not discriminate on age

Results — breast cancer and gender

Results — protein expresion heatmap

Results — dimentionality reduction

Results — K-means clustering

Results — ANN model’s structure

Results — ANN performance

Discussion

  • What could have been better

  • further work

The end